Generic Methods for S3 class cauphylm
.
# S3 method for cauphylm
print(x, digits = max(3, getOption("digits") - 3), ...)
# S3 method for cauphylm
vcov(object, ...)
# S3 method for cauphylm
logLik(object, ...)
# S3 method for logLik.cauphylm
AIC(object, k = 2, ...)
# S3 method for cauphylm
AIC(object, k = 2, ...)
# S3 method for cauphylm
predict(object, newdata = NULL, ...)
# S3 method for cauphylm
confint(object, parm, level = 0.95, ...)
# S3 method for cauphylm
coef(object, ...)
an object of class "phylolm"
.
number of digits to show in summary method.
further arguments to methods.
an object of class cauphylm
.
numeric, the penalty per parameter to be used; the default k = 2
is the classical AIC.
an optional data frame to provide the predictor values at which predictions should be made. If omitted, the fitted values are used. Currently, predictions are made for new species whose placement in the tree is unknown. Only their covariate information is used. The prediction for the trend model is not currently implemented.
a specification of which parameters are to be given confidence intervals, either a vector of numbers or a vector of names. If missing, all parameters are considered.
the confidence level required.
Same value as the associated methods from the stats
package:
# Simulate tree and data
set.seed(1289)
phy <- ape::rphylo(20, 0.1, 0)
error <- rTraitCauchy(n = 1, phy = phy, model = "cauchy",
parameters = list(root.value = 0, disp = 0.1))
x1 <- ape::rTraitCont(phy, model = "BM", sigma = 0.1, root.value = 0)
trait <- 3 + 2*x1 + error
# Fit the data
fit <- cauphylm(trait ~ x1, phy = phy)
fit
#> Call:
#> cauphylm(formula = trait ~ x1, phy = phy)
#>
#> AIC logLik
#> 77.8 -35.9
#>
#> Parameter estimate(s) using ML:
#> dispersion: 0.05249818
#>
#> Coefficients:
#> (Intercept) x1
#> 2.005913 1.421920
# vcov matrix
vcov(fit)
#> (Intercept) x1 disp
#> (Intercept) 0.6470977107 0.1291299896 0.0009311013
#> x1 0.1291299896 0.1399242443 0.0002061902
#> disp 0.0009311013 0.0002061902 0.0002891545
# Approximate confidence intervals
confint(fit)
#> Approximated asymptotic confidence interval using the Hessian.
#> 2.5 % 97.5 %
#> (Intercept) 0.42927112 3.58255462
#> x1 0.68876658 2.15507244
#> disp 0.01916989 0.08582647
# log likelihood of the fitted object
logLik(fit)
#> 'log Lik.' -35.89783 (df=3)
# AIC of the fitted object
AIC(fit)
#> [1] 77.79565
# predicted values
predict(fit)
#> t1 t2 t3 t4 t5 t6 t7 t8
#> 0.7028928 1.5519815 1.7258657 1.7662845 1.2772374 1.8690039 2.1319177 2.0970362
#> t9 t10 t11 t12 t13 t14 t15 t16
#> 1.1722677 1.9586478 1.6825041 1.6882501 2.2393014 1.9425933 1.8442025 2.2179683
#> t17 t18 t19 t20
#> 1.5230505 2.2757195 1.0490475 1.3168765
# coefficients
coef(fit)
#> (Intercept) x1 disp
#> 2.00591287 1.42191951 0.05249818